[SLP]Fix detection of matching splat vector
Need to check, that the mask of the potentially matching splat node is
not less defined than the requested mask to avoid poison propagation and
incorrect code.
Fixes #135113
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 2efe107..444bd08 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -10617,7 +10617,11 @@
/*IsStrict=*/true) ||
(Shuffle && Mask.size() == Shuffle->getShuffleMask().size() &&
Shuffle->isZeroEltSplat() &&
- ShuffleVectorInst::isZeroEltSplatMask(Mask, Mask.size())));
+ ShuffleVectorInst::isZeroEltSplatMask(Mask, Mask.size()) &&
+ all_of(enumerate(Mask), [&](const auto &P) {
+ return P.value() == PoisonMaskElem ||
+ Shuffle->getShuffleMask()[P.index()] == 0;
+ })));
}
V = Op;
return false;
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/identity-match-splat-less-defined.ll b/llvm/test/Transforms/SLPVectorizer/X86/identity-match-splat-less-defined.ll
index d6449c5..d6f0b76 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/identity-match-splat-less-defined.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/identity-match-splat-less-defined.ll
@@ -7,7 +7,8 @@
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 poison>
; CHECK-NEXT: [[TMP3:%.*]] = or <4 x i32> [[TMP2]], <i32 0, i32 0, i32 0, i32 poison>
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> poison, <16 x i32> <i32 0, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
-; CHECK-NEXT: [[TMP5:%.*]] = or <4 x i32> [[TMP2]], zeroinitializer
+; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP5:%.*]] = or <4 x i32> [[TMP25]], zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <24 x i32> <i32 0, i32 0, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 3, i32 3, i32 3>
; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> poison, <64 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <64 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 3, i32 3, i32 3, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
